Spaces:
Runtime error
Runtime error
File size: 3,005 Bytes
2089314 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import cv2
import re
import pytesseract
import numpy as np
import gradio as gr
import pandas as pd
from matplotlib import pyplot as plt
# get grayscale image
def get_grayscale(image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# noise removal
def remove_noise(image):
return cv2.medianBlur(image,5)
#thresholding
def thresholding(image, thresh_hold=0, which='ostu'):
if which == 'ostu':
return cv2.threshold(image, thresh_hold, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
elif which == 'simple':
_, img = cv2.threshold(image,thresh_hold,255,cv2.THRESH_BINARY)
return img
elif which == 'adaptive':
return cv2.adaptiveThreshold(image, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
#dilation
def dilate(image):
kernel = np.ones((5,5),np.uint8)
return cv2.dilate(image, kernel, iterations = 1)
#erosion
def erode(image):
kernel = np.ones((5,5),np.uint8)
return cv2.erode(image, kernel, iterations = 1)
#opening - erosion followed by dilation
def opening(image):
kernel = np.ones((5,5),np.uint8)
return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)
#canny edge detection
def canny(image):
return cv2.Canny(image, 100, 200)
#skew correction
def deskew(image):
coords = np.column_stack(np.where(image > 0))
angle = cv2.minAreaRect(coords)[-1]
if angle < -45:
angle = -(90 + angle)
else:
angle = -angle
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
return rotated
#template matching
def match_template(image, template):
return cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)
def show_cvimg(img, figsize=(15, 15)):
fig, ax = plt.subplots(dpi=80, figsize=figsize)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
ax.imshow(img)
def extract_purchased_items(txt):
pat = '.*\s*(FB|FA|NB)'
p = re.compile("(.*) (\d+[,\.\/\:\']*\d+) (FB|FA|NB)")
txts = txt.split('\n')
items = []
not_parsed = []
for t in txts:
if re.match(pat, t):
result = p.search(t)
if result is not None:
items.append({'item': result.group(1),
'price': re.sub('[,\.\/\:\']', '.', result.group(2)),
'type': result.group(3)
})
else:
not_parsed.append({'not parsed': t})
return pd.DataFrame(items), pd.DataFrame(not_parsed)
def parse_receipt(img, **kwargs):
# preprocessing
gray = get_grayscale(img)
thresh = thresholding(gray, **kwargs)
# ocr
custom_config = r'--oem 3 --psm 6'
txt = pytesseract.image_to_string(thresh, config=custom_config)
return extract_purchased_items(txt)
iface = gr.Interface(fn=parse_receipt, inputs="image", outputs=["dataframe", "dataframe"])
iface.launch() |